修改上一例，改为多线程执行

修改之前的爬虫，改为多线程下载，进行了简单粗暴的修改

import threading
import time
import queue
import urllib.request
import re
import os

#打开网页
def openURL(web):
    headers={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36 QIHU 360SE'}
    req=urllib.request.Request(url=web,headers=headers)
    data=urllib.request.urlopen(req)
    return data.read().decode('UTF-8')

#提取子页面链接及子页面名称
def filterHTML(html):
    result=[]
    base_link='http://www.ivsky.com'
    link_re = re.compile(r'class="il_img"><a href="(.*?)" title="(.*?)"')
    for link,title in link_re.findall(html):
        link=base_link+link
        result.append((link,title))
    return result

#在子页面提取图片地址
def searchHTML(html):
    result=[]
    base_link='http://img.ivsky.com'
    msg_re=re.compile(r'arctitle=.*\((.*?)张.*?imgURL=\'(.*?)\'.*?aid=\'(.*?)\'')
    num,url,name=msg_re.findall(html)[0]
    #print('num=%s\nurl=%s\nname=%s' % (num,url,name))
    num=int(num)
    link=base_link+url
    result.append((name,link))
    pos=link.rfind('.')
    part1=link[:pos]
    part2=link[pos:]
    #判断是否有'-001'编号
    if len(part1.split('-'))==1:
        begin=1
    else:
        begin=2
        part1=part1.split('-')[0]
    for i in range(begin,num):
        sign='-%03d' % i
        new_name = str(int(name)+i)
        new_link = part1+sign+part2
        result.append((new_name,new_link))
    
    return result

#每个线程调用函数down_pic,从给出的链接处下载图片
def down_pic(url,path):
    sub_html=openURL(url)
    link=filterHTML(sub_html)[0][0]
    html=openURL(link)
    for pic_name,pic_url in searchHTML(html):
        try:
            pic_name+='.jpg'
            print('%s:url=%s' %(threading.current_thread().name,pic_url))
            urllib.request.urlretrieve(pic_url,os.path.join(path,pic_name))
        except:
            print('下载失败')
    print('%s 下载完成' % (os.path.split(path)[-1]))


def main():
    base_path='PicDownload'
    if not os.path.isdir(base_path):
        os.makedirs(base_path)
    web='http://www.ivsky.com/tupian/index_5.html'
    q=queue.Queue()
    html=openURL(web)
    for link,title in filterHTML(html):
        #建立文件夹
        path=os.path.join(base_path,title)
        if not os.path.isdir(path):
            os.makedirs(path)
        q.put((link,path))
    while not q.empty():
        sub_web=q.get()
        threading.Thread(target=down_pic,args=(sub_web[0],sub_web[1])).start()
    
    

if __name__=='__main__':
    main()